A Multi-Scale Tensor Network Architecture for Classification and Regression

Abstract

We present an algorithm for supervised learning using tensor networks, employing a step of preprocessing the data by coarse-graining through a sequence of wavelet transformations. We represent these transformations as a set of tensor network layers identical to those in a multi-scale entanglement renormalization ansatz (MERA) tensor network, and perform supervised learning and regression tasks through a model based on a matrix product state (MPS) tensor network acting on the coarse-grained data. Because the entire model consists of tensor contractions (apart from the initial non-linear feature map), we can adaptively fine-grain the optimized MPS model backwards through the layers with essentially no loss in performance. The MPS itself is trained using an adaptive algorithm based on the density matrix renormalization group (DMRG) algorithm. We test our methods by performing a classification task on audio data and a regression task on temperature time-series data, studying the dependence of training accuracy on the number of coarse-graining layers and showing how fine-graining through the network may be used to initialize models with access to finer-scale features.

References in corpus (15)

• Deep Learning in Neural Networks: An Overview
• Efficient classical simulation of slightly entangled quantum computations
• Efficient simulation of one-dimensional quantum many-body systems
• Entanglement renormalization
• A class of quantum many-body states that can be efficiently simulated
• Algorithms for entanglement renormalization
• Unsupervised Generative Modeling Using Matrix Product States
• Supervised Learning with Quantum-Inspired Tensor Networks
• Entanglement renormalization and wavelets
• Multigrid Algorithms for Tensor Network States
• Tensor Networks for Big Data Analytics and Large-Scale Optimization Problems
• Deep Learning and Quantum Entanglement: Fundamental Connections with Implications to Network Design
• Representation and design of wavelets using unitary circuits
• Expressive power of tensor-network factorizations for probabilistic modeling, with applications from hidden Markov models to quantum machine learning
• Machine learning assisted measurement of local topological invariants

Cited by in corpus (4)

• Mutual Information Scaling for Tensor Network Machine Learning
• Anomaly Detection with Tensor Networks
• Language Modeling with Reduced Densities
• Multi-layered tensor networks for image classification